[WF1] Optical Network Sensing and System Modeling

9:30 AM - 9:45 AM JST(12:30 AM - 12:45 AM UTC)

[WF1-2] Joint Sensing of Two Independent Failures in Optical Network Using a Single Variational Auto-Encoder Model

○Yuwa Yamamoto¹, Akira Hirano¹, Sugang Xu², Yoshinari Awaji² (1. Tokyo Denki University (Japan), 2. National Institute of Information and Communications Technology (Japan))

Keywords:

Optical core/metro network architecture,design,control,and management,Artificial intelligence and machine learning for optical network design,control,and management

We conducted unsupervised learning of two independent failures including optical fiber bending and ROADM optical filter shift using a VAE model. We successfully detected these anomalies with sufficient high accuracy of over 90%.